Real-time forecasting of electricity demand in a streams-based architecture with applications
Abstract
A streams platform is used. Multiple streams of electricity usage data are received, each from an electrical meter providing periodic updates to electrical usage for devices connected to the electrical meter. Weather information is received corresponding to locations where the electrical meters are. Real-time predictive modeling of electricity demand is performed based on the received multiple streams of electricity usage data and the received weather information, at least by performing: updating a state space model for electrical load curves using the usage data from the streams and the weather, wherein the updating uses current load observations for the multiple streams for a current time period; and creating forecast(s) for the electricity demand. The forecast(s) of the electricity demand are output. Appliance-level predictions may be made and used, and substitution effects and load management functions may be performed.
- Inventors:
- Issue Date:
- Research Org.:
- International Business Machines Corp., Armonk, NY (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1568307
- Patent Number(s):
- 10282795
- Application Number:
- 15/189,173
- Assignee:
- International Business Machines Corporation (Armonk, NY)
- Patent Classifications (CPCs):
-
G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
G - PHYSICS G06 - COMPUTING G06Q - DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES
- DOE Contract Number:
- OE0000190
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 06/22/2016
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Ghosh, Soumyadip, Hosking, Jonathan R., Natarajan, Ramesh, Subramanian, Shivaram, and Zhang, Xiaoxuan. Real-time forecasting of electricity demand in a streams-based architecture with applications. United States: N. p., 2019.
Web.
Ghosh, Soumyadip, Hosking, Jonathan R., Natarajan, Ramesh, Subramanian, Shivaram, & Zhang, Xiaoxuan. Real-time forecasting of electricity demand in a streams-based architecture with applications. United States.
Ghosh, Soumyadip, Hosking, Jonathan R., Natarajan, Ramesh, Subramanian, Shivaram, and Zhang, Xiaoxuan. Tue .
"Real-time forecasting of electricity demand in a streams-based architecture with applications". United States. https://www.osti.gov/servlets/purl/1568307.
@article{osti_1568307,
title = {Real-time forecasting of electricity demand in a streams-based architecture with applications},
author = {Ghosh, Soumyadip and Hosking, Jonathan R. and Natarajan, Ramesh and Subramanian, Shivaram and Zhang, Xiaoxuan},
abstractNote = {A streams platform is used. Multiple streams of electricity usage data are received, each from an electrical meter providing periodic updates to electrical usage for devices connected to the electrical meter. Weather information is received corresponding to locations where the electrical meters are. Real-time predictive modeling of electricity demand is performed based on the received multiple streams of electricity usage data and the received weather information, at least by performing: updating a state space model for electrical load curves using the usage data from the streams and the weather, wherein the updating uses current load observations for the multiple streams for a current time period; and creating forecast(s) for the electricity demand. The forecast(s) of the electricity demand are output. Appliance-level predictions may be made and used, and substitution effects and load management functions may be performed.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {5}
}
Works referenced in this record:
Model-based load demand control
patent, October 2015
- Beveridge, Robert Allen
- US Patent Document 9,163,828
System and method for forecasting energy usage load
patent, June 2003
- Afshari, Afshin
- US Patent Document 6,577,962
Energy Management Systems and Methods
patent-application, September 2011
- Irving, Gary W.
- US Patent Application 12/975188; 20110231320
Managed virtual power plant utilizing aggregated storage
patent, September 2013
- Parsonnet, Brian; Narayanamurthy, Ramachandran
- US Patent Document 8,528,345
Method and system for forecasting power requirements using granular metrics
patent, June 2016
- Haghighat-Kashani, Ali; Cheam, Janice Tze-Nee; Hallam, Jonathan Mark
- US Patent Document 9,366,704